Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
110 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Even-Ifs From If-Onlys: Are the Best Semi-Factual Explanations Found Using Counterfactuals As Guides? (2403.00980v2)

Published 1 Mar 2024 in cs.AI

Abstract: Recently, counterfactuals using "if-only" explanations have become very popular in eXplainable AI (XAI), as they describe which changes to feature-inputs of a black-box AI system result in changes to a (usually negative) decision-outcome. Even more recently, semi-factuals using "even-if" explanations have gained more attention. They elucidate the feature-input changes that do not change the decision-outcome of the AI system, with a potential to suggest more beneficial recourses. Some semi-factual methods use counterfactuals to the query-instance to guide semi-factual production (so-called counterfactual-guided methods), whereas others do not (so-called counterfactual-free methods). In this work, we perform comprehensive tests of 8 semi-factual methods on 7 datasets using 5 key metrics, to determine whether counterfactual guidance is necessary to find the best semi-factuals. The results of these tests suggests not, but rather that computing other aspects of the decision space lead to better semi-factual XAI.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (37)
  1. On the robustness of interpretability methods. arXiv preprint arXiv:1806.08049, 2018.
  2. ”even if…”–diverse semifactual explanations of reject. arXiv preprint arXiv:2207.01898, 2022.
  3. Even if explanations: Prior work, desiderata & benchmarks for semi-factual xai. In IJCAI-23, pages 6526–6535, 8 2023.
  4. Jonathan Bennett. A philosophical guide to conditionals. Clarendon Press, 2003.
  5. Nice: an algorithm for nearest instance counterfactual explanations. Data Mining and Knowledge Discovery, pages 1–39, 2023.
  6. Kleor: A knowledge lite approach to explanation oriented retrieval. Computing and Informatics, 25(2-3):173–193, 2006.
  7. Multi-objective counterfactual explanations. In International Conference on Parallel Problem Solving from Nature, pages 448–469. Springer, 2020.
  8. Explanation oriented retrieval. In European Conference on Case-Based Reasoning, pages 157–168. Springer, 2004.
  9. Factual and counterfactual explanations for black box decision making. IEEE Intelligent Systems, 34(6):14–23, 2019.
  10. Robust counterfactual explanations for neural networks with probabilistic guarantees. arXiv preprint arXiv:2305.11997, 2023.
  11. To trust or not to trust a classifier. Advances in neural information processing systems, 31, 2018.
  12. A survey of algorithmic recourse: contrastive explanations and consequential recommendations. ACM Computing Surveys, 55(5):1–29, 2022.
  13. Algorithmic recourse: from counterfactual explanations to interventions. In Proceedings of the 2021 ACM conference on fairness, accountability, and transparency, pages 353–362, 2021.
  14. If only we had better counterfactual explanations. In Proceedings of the 30th International Joint Conference on Artificial Intelligence (IJCAI-21), 2021.
  15. Good counterfactuals and where to find them: A case-based technique for generating counterfactuals for explainable ai (xai). In Proceedings of the 28th International Conference on Case-Based Reasoning (ICCBR-20), pages 163–178. Springer, 2020.
  16. The utility of “even if” semi-factual explanation to optimize positive outcomes. In NeurIPs-23, 2023.
  17. On generating plausible counterfactual and semi-factual explanations for deep learning. In Proceedings of the 35th AAAI Conference on Artificial Intelligence (AAAI-21), pages 11575–11585, 2021.
  18. A rationale-centric framework for human-in-the-loop machine learning. arXiv preprint arXiv:2203.12918, 2022.
  19. Semifactual ”even if” thinking. Thinking & Reasoning, 8(1):41–67, 2002.
  20. Alterfactual explanations–the relevance of irrelevance for explaining ai systems. arXiv preprint arXiv:2207.09374, 2022.
  21. Tim Miller. Explanation in artificial intelligence: Insights from the social sciences. Artificial Intelligence, 267:1–38, 2019.
  22. Explaining machine learning classifiers through diverse counterfactual explanations. In Proceedings of the Facct-2020, pages 607–617, 2020.
  23. The best way to instil confidence is by being right. In International Conference on Case-Based Reasoning, pages 368–381. Springer, 2005.
  24. Gaining insight through case-based explanation. Journal of Intelligent Info Systems, 32:267–295, 2009.
  25. Natural example-based explainability: a survey. arXiv preprint arXiv:19, 2023.
  26. ” why should i trust you?” explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD-16, pages 1135–1144, 2016.
  27. Geco: Quality counterfactual explanations in real time. arXiv preprint arXiv:2101.01292, 2021.
  28. A few good counterfactuals: generating interpretable, plausible and diverse counterfactual explanations. In International Conference on Case-Based Reasoning, pages 18–32. Springer, 2022.
  29. Actionable recourse in linear classification. In Proceedings of the Facct-19, pages 10–19, 2019.
  30. Conditional generative models for counterfactual explanations. arXiv preprint arXiv:2101.10123, 2021.
  31. This changes to that: Combining causal and non-causal explanations to generate disease progression in capsule endoscopy. arXiv preprint arXiv:2212.02506, 2022.
  32. Counterfactual explanations and algorithmic recourses for machine learning: a review. arXiv preprint arXiv:2010.10596, 2020.
  33. Counterfactual explanations without opening the black box. Harv. JL & Tech., 31:841, 2017.
  34. Applying class-to-class siamese networks to explain classifications with supportive and contrastive cases. In Case-Based Reasoning Research and Development: 28th International Conference, ICCBR 2020, Salamanca, Spain, June 8–12, 2020, Proceedings, pages 245–260. Springer, 2020.
  35. Learning adaptations for case-based classification: A neural network approach. In International Conference on Case-Based Reasoning, pages 279–293. Springer, 2021.
  36. Interpreting neural networks using flip points. arXiv preprint arXiv:1903.08789, 2019.
  37. Generating counterfactual images: Towards a c2c-vae approach. In 4th Workshop on XCBR: Case-Based Reasoning for the Explanation of Intelligent Systems, 2022.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (2)
  1. Saugat Aryal (2 papers)
  2. Mark T. Keane (27 papers)
Citations (4)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets